System and method to create object detection scan plans

Abstract

A system for generating a scanning list of objects to be scanned for creating an image data set for use in object detection training. A list of the objects to be scanned is received. An initial set of object combinations of the objects to be scanned is enumerated. A modified set of object combinations is generated by applying rules to each object combination in the initial set of object combinations, the rules including identifying known objects based on inclusion of other objects in the combination, and the rules including identifying unscannable objects based on inclusion of other objects in the combination. The scanning list is generated by selecting object combinations from the modified set of object combinations until all objects to be scanned appear at least once in the scanning list.

What is claimed is: 
     
         1 . An augmented reality system, comprising:
 a computing system having an object model, the object model generated by:   enumerating an initial set of object combinations of objects to be scanned;   generating a modified set of object combinations by applying rules to each object combination in the initial set of object combinations, the rules including identifying known objects based on inclusion of other objects in the combination, and the rules including identifying unscannable objects based on inclusion of other objects in the combination;   generating a scanning list by selecting object combinations from the modified set of object combinations until all objects to be scanned appear at least once in the scanning list;   
       generating the object model by training an object detector to identify the objects using a labeled image data set of the images from scans of the objects in accordance with the scanning list;
 the computing system adapted to establish a communication session between the computing system and a user device; 
 the computing system adapted to receive an image from the user device; 
 
       the computing system adapted to identify objects in the image using the object model; and
 the computing system adapted to transmit an annotation of the image to the user device for presentation. 
 
     
     
         2 . The system of  claim 1 , wherein:
 each of the objects to be scanned has different states; and   the rules include marking known object states based on states of other objects in the combination, and the rules include marking unscannable objects based on states of other objects in the combination.   
     
     
         3 . The system of  claim 2 , wherein the computing system is adapted to generate the scanning list by selecting combinations from the modified set of state combinations until all states of all parts appear at least once in the scanning list. 
     
     
         4 . The system of  claim 2 , wherein the different states comprise an open state and a closed state. 
     
     
         5 . The system of  claim 2 , wherein the objects to be scanned are parts of a product. 
     
     
         6 . The system of  claim 2 , wherein the computing system is adapted to enumerate the initial set of state combinations using fractional factorial design of experiment with resolution III or IV. 
     
     
         7 . The system of  claim 2 , wherein the computing system is adapted to enumerate the initial set of state combinations, generate a modified set of state combinations, and generate the scanning list multiple times, and to select a selected scanning list having a least amount of sets. 
     
     
         8 . The system of  claim 2 , wherein the computing system is adapted to reorder the scanning list to make it more efficient for scanning. 
     
     
         9 . The system of  claim 2 , wherein the computing system comprises a plurality of processors in communication over a network. 
     
     
         10 . The system of  claim 1 , wherein:
 each of the objects to be scanned has different states;   the rules include marking known object states based on states of other objects in the combination, and the rules include marking unscannable objects based on states of other objects in the combination; and   the computing system is adapted to generate the scanning list by selecting combinations from the modified set of state combinations until all states of all parts appear at least once in the scanning list.   
     
     
         11 . The system of  claim 1 , wherein the computing system is adapted to enumerate the initial set of state combinations, generate a modified set of state combinations, and generate the scanning list multiple times, and to select a selected scanning list having a least amount of sets. 
     
     
         12 . The system of  claim 1 , wherein the augmented reality system comprises a support platform and the identified objects are parts of a product that is being supported. 
     
     
         13 . The system of  claim 12 , wherein the computing system is adapted to provide self-guidance support of the product comprising instructional information. 
     
     
         14 . The system of  claim 12 , wherein the computing system is adapted to provide tasks for troubleshooting support of the product, and the computing system is adapted to detect whether a task has been completed. 
     
     
         15 . The system of  claim 12 , further comprising a database of workflows;
 the computing system adapted to select a selected workflow from the database of workflows using an identification of the product; and   wherein the selected workflow includes instructions provided to the user device.